English

Analytical Methods for Interpretable Ultradense Word Embeddings

Computation and Language 2019-09-16 v2

Abstract

Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In this work, we investigate three methods for making word spaces interpretable by rotation: Densifier (Rothe et al., 2016), linear SVMs and DensRay, a new method we propose. In contrast to Densifier, DensRay can be computed in closed form, is hyperparameter-free and thus more robust than Densifier. We evaluate the three methods on lexicon induction and set-based word analogy. In addition we provide qualitative insights as to how interpretable word spaces can be used for removing gender bias from embeddings.

Keywords

Cite

@article{arxiv.1904.08654,
  title  = {Analytical Methods for Interpretable Ultradense Word Embeddings},
  author = {Philipp Dufter and Hinrich Schütze},
  journal= {arXiv preprint arXiv:1904.08654},
  year   = {2019}
}

Comments

EMNLP 2019

R2 v1 2026-06-23T08:43:34.808Z